ClawHub
Back to skill

Security audit

cosprompt

Security checks for vulnerabilities and agentic risk

Overview

This prompt-generation skill is mostly coherent, but it needs review because it includes under-18 character presets in a cosplay/glamour prompt workflow without clear safety boundaries.

Review or remove the under-18 age presets before installing, or add explicit rules that minors must only be depicted in age-appropriate, non-sexual contexts with no suggestive clothing, pose, body emphasis, or mood tags. Also consider narrowing tool permissions by removing Write/Edit unless you specifically want the skill to modify files.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Ssd 4

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The age presets explicitly include minors ('少女 16-18', '萝莉 12-15') alongside styling cues such as '清纯可爱' and placement in a cosplay/poster prompt generator that also supports beauty, glamour, and '魅力/诱惑' framing elsewhere in the skill. Even without an explicit sexual instruction in that table, this creates a clear pathway for generating sexualized or fetishized depictions of minors, especially because the system autonomously fills style, costume, mood, and pose dimensions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill is written entirely in Chinese and operationally assumes Chinese-language interaction without stating that output language should follow the user's preference. In practice, this can override user expectations, cause unintended language switching, and make downstream generated content less reviewable or understandable for users operating in other languages.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger metadata is overly broad ('用户需要生成 AI 绘图提示词、角色海报 prompt、Cosplay 海报提示词'), which can cause the skill to activate in contexts where the user did not explicitly request this specialized behavior. Over-broad activation increases the chance of unintended browsing, content generation, and application of the skill's assumptions to adjacent requests, reducing user control and creating prompt-scope confusion.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.